llama.cpp
6a30bf3e - batched : add NGL arg

Login via GitHub
Home
Pricing
FAQ
Install

Login via GitHub

Commit

2 years ago

batched : add NGL arg

References

#3749 - cuda : add batched cuBLAS GEMM for faster attention

Author

ggerganov

ggerganov

Parents

FAQ Terms Privacy Refunds Impressum

Loading